检索结果-内蒙古大学图书馆

ControlVideo: conditional control for one-shot text-driven video editing and beyond

science China(Information sciences) 2025年第3期68卷 150-162页

作者： Min ZHAO Rongzhen WANG Fan BAO Chongxuan LI Jun ZHU Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML CenterTsinghua Laboratory of Brain and Intelligence Lab Tsinghua University ShengShu Technology Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods Pazhou Laboratory (Huangpu)

This paper presents ControlVideo for text-driven video editing — generating a video that aligns with a given text while preserving the structure of the source video. Building on a pre-trained text-to-image diffusion model, ControlVideo enhances the fidelity and temporal consistency by incorporating additional conditions(such as edge maps), and fine-tuning the key-frame and temporal attention on the source video-text pair via an in-depth exploration of the design space. Extensive experimental results demonstrate that ControlVideo outperforms various competitive baselines by delivering videos that exhibit high fidelity w.r.t. the source content, and temporal consistency, all while aligning with the text. By incorporating low-rank adaptation layers into the model before training, ControlVideo is further empowered to generate videos that align seamlessly with reference images. More importantly, ControlVideo can be readily extended to the more challenging task of long video editing(e.g., with hundreds of frames), where maintaining long-range temporal consistency is crucial. To achieve this, we propose to construct a fused ControlVideo by applying basic ControlVideo to overlapping short video segments and key frame videos and then merging them by pre-defined weight functions. Empirical results validate its capability to create videos across 140 frames, which is approximately 5.83 to 17.5 times more than what previous studies achieved. The code is available at https://***/thu-ml/controlvideo.

关键词： diffusion models controllable generation text-driven editing video editing long video editing

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal deformation analysis of glaciers and surrounding landscapes in the Shishapangma region using InSAR techniques

引用

Journal of Mountain science 2025年第1期22卷 210-229页

作者： LIANG Wenli LIU Rui JI Qin KOU Pinglang Chongqing Key Laboratory of GIS Application School of Geography and TourismChongqing Normal UniversityChongqing 401331China National Earth System Science Data Center Beijing 100000China Chongqing Engineering Research Center of Spatial Big Data Intelligent Technology Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Tourism Multisource Data Perception and Decision Ministry of Culture and Tourism(TMDPDMCT)Chongqing University of Posts and TelecommunicationsChongqing 400065China

Glacier dynamics in the Himalayan midlatitudes,particularly in regions like the Shishapangma,are not yet fully understood,especially the localized topographic and climatic impacts on glacier *** study analyzes the spatiotemporal characteristics of glacier surface deformation in the Shishapangma region using the Small Baseline Subset(SBAS)Interferometric Synthetic Aperture Radar(In SAR)*** analysis reveals an average deformation rate of-4.02±17.65 mm/yr across the entire study area,with glacier regions exhibiting significantly higher rates of uplift(16.87±13.20 mm/yr)and subsidence(20.11±14.55 mm/yr)compared to non-glacier *** identifies significant surface lowering on the mountain flanks and localized uplift in certain catchments,emphasizing the higher deformation rates in glacial areas compared to non-glacial *** found a strong positive correlation between temperature and cumulative deformation(correlation coefficient of 0.63),particularly in glacier areas(0.82).The research highlights the role of temperature as the primary driver of glacier wastage,particularly at lower elevations,with strong correlations found between temperature and cumulative *** also indicates the complex interactions between topographic features,notably,slope gradient,which shows a positive correlation with subsidence rates,especially for slopes below 35°.South-,southwest-,and west-facing slopes exhibit significant uplift,while north-,northeast-,and east-facing slopes predominantly ***,we identified transition zones between debris-covered glaciers and clean ice as areas of most intense deformation,with average rates exceeding 30 mm/yr,highlighting these as potential high-risk zones for *** study comprehensively analyzes the deformation characteristics in both glacier and non-glacier areas in the Shishapangma region,revealing the complex interplay of topographic,climatic,and hydrological factors influencing glacier dynamic

关键词： Glacier melting SBAS-InSAR Topographic factors Temperature change Middle Himalayas

来源：评论

学校读者我要写书评

暂无评论

Application of improved virtual sample and sparse representation in face recognition

引用

CAAI Transactions on Intelligence technology 2023年第4期8卷 1391-1402页

作者： Yongjun Zhang Zewei Wang Xuexue Zhang Zhongwei Cui Bob Zhang Jinrong Cui Lamin LJanneh College of Computer Science and Technology Guizhou UniversityGuiyangChina Big Data Science and Intelligent Engineering Research Institute Guizhou Education UniversityGuiyangChina School of Mathematics and Big Data Guizhou Education UniversityGuiyangChina Department of Computer and Information Science University of MacaoAvenida da UniversidadeTaipaMacaoChina School of Mathematics and Information South China Agricultural UniversityGuangzhouChina

Sparse representation plays an important role in the research of face *** a deformable sample classification task,face recognition is often used to test the performance of classification *** face recognition,differences in expression,angle,posture,and lighting conditions have become key factors that affect recognition ***,there may be significant differences between different image samples of the same face,which makes image classification very ***,how to build a robust virtual image representation becomes a vital *** solve the above problems,this paper proposes a novel image classification ***,to better retain the global features and contour information of the original sample,the algorithm uses an improved non‐linear image representation method to highlight the low‐intensity and high‐intensity pixels of the original training sample,thus generating a virtual ***,by the principle of sparse representation,the linear expression coefficients of the original sample and the virtual sample can be calculated,*** obtaining these two types of coefficients,calculate the distances between the original sample and the test sample and the distance between the virtual sample and the test *** two distances are converted into distance ***,a simple and effective weight fusion scheme is adopted to fuse the classification scores of the original image and the virtual *** fused score will determine the final classification *** experimental results show that the proposed method outperforms other typical sparse representation classification methods.

关键词： representation sample image

来源：评论

学校读者我要写书评

暂无评论

ViGT: proposal-free video grounding with a learnable token in the transformer

引用

science China(Information sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

A robust tensor watermarking algorithm for diffusion-tensor images

引用

Frontiers of Information technology & Electronic Engineering 2024年第3期25卷 384-397页

作者： Chengmeng LIU Zhi LI Guomei WANG Long ZHENG State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China

Watermarking algorithms that use convolution neural networks have exhibited good robustness in studies of deep learning ***,after embedding watermark signals by convolution,the feature fusion eficiency of convolution is relatively low;this can easily lead to distortion in the embedded *** distortion occurs in medical images,especially in diffusion tensor images(DTIs),the clinical value of the DTI is *** address this issue,a robust watermarking algorithm for DTIs implemented by fusing convolution with a Transformer is proposed to ensure the robustness of the watermark and the consistency of sampling distance,which enhances the quality of the reconstructed image of the watermarked DTIs after embedding the watermark *** the watermark-embedding network,Ti-weighted(Tlw)images are used as prior *** correlation between T1w images and the original DTI is proposed to calculate the most significant features from the T1w images by using the Transformer *** maximum of the correlation is used as the most significant feature weight to improve the quality of the reconstructed *** the watermark extraction network,the most significant watermark features from the watermarked DTI are adequately learned by the Transformer to robustly extract the watermark signals from the watermark *** results show that the average peak signal-to-noise ratio of the watermarked DTI reaches 50.47 dB,the diffusion characteristics such as mean diffusivity and fractional anisotropy remain unchanged,and the main axis deflection angleαAc is close to *** proposed algorithm can effectively protect the copyright of the DTI and barely affects the clinical diagnosis.

关键词： Robust watermarking algorithm Transformer Image reconstruction Diffusion tensor images Soft attention Hard attention Tl-weighted images

来源：评论

学校读者我要写书评

暂无评论

Object Detection with YOLO Version 3 for big data 1

引用

5th International Conference on Information Systems and Management science, ISMS 2022

作者： Saxena, Rajat Dubey, Shatendra Karna, Vishma Kumar Big Data Lab Department of Computer Science and Engineering Shri Vaishnav Institute of Information Technology Shri Vaishnav Vidyapeth Vishwavidyalaya Indore India Big Data Lab Department of Information Technology NRI Institute of Information Science and Technology Bhopal India

ISBN: (数字)9783031311536

ISBN: (纸本)9783031311529

Object detection is the most vital task for the application of computer vision. The You only Look Once (YOLO) version3 is the most promising technique used for deep learning-based object detection. It is the k-means cluster method, which estimates initial weight and height of the predicting bounding boxes that are sensitive to the initial cluster centers. This paper focuses on study of approaches for efficient object detection techniques in the field of computer vision. The improvement in the accuracy had been studied based on the deep learning techniques. It aims to develop an online tool for a better study about the object detection techniques as a platform to review the object detection in both online and offline images. A popular state of art object detection algorithm called YOLOv3 which is trained on COCO and ImageNet. The result obtained in the developed online tool has shown a positive result with a possibility in detecting the most common objects available in this real world. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Mechanical properties of thermoelectric generators

引用

Journal of Materials science & technology 2023年第17期148卷 64-74页

作者： Xin Bao Shuaihang Hou Zhixin Wu Xiaodong Wang Li Yin Yijie Liu Huolun He Sichen Duan Baolin Wang Jun Mao Feng Cao Qian Zhang School of Materials Science and Engineering and Institute of Materials Genome&Big DataHarbin Institute of TechnologyShenzhen518055China State Key Laboratory of Advanced Welding and Joining Harbin Institute of TechnologyHarbin150001China School of Science Harbin Institute of TechnologyShenzhen518055China

To satisfy the requirements of practical applications,thermoelectric generators should be highly efficient and mechanically ***,progress in designing high-performance thermoelectric generators has been ***,the mechanical properties of thermoelectric generators are still *** this review,studies on the mechanical properties of thermoelectric generators are *** me-chanical properties of bulk thermoelectric generators will be first *** this section,the mechan-ical properties of thermoelectric materials and the strategies for improving their mechanical properties are *** the device’s failure usually occurs at the interface between the thermoelectric ma-terials and electrode,the joint strength of electrodes and thermoelectric materials will be *** that,the mechanical properties of the inorganic thin-film thermoelectric devices will be *** the figure of merit for the flexibility of thermoelectric materials depends on the film thickness,elastic modulus,and yield strength,the synthesis methods of thin-film thermoelectric materials will be ***,this review will be concluded with a discussion on flexible organic thermoelectric de-vices and flexible devices using bulk legs.

关键词： Thermoelectric generator Mechanical properties Interface Joint strength

来源：评论

学校读者我要写书评

暂无评论

MTSC-Net:A Semi-Supervised Counting Network for Estimating the Number of Slash pine New Shoots

引用

植物表型组学（英文） 2024年第4期6卷 953-966页

作者： Zhaoxu Zhang Yanjie Li Yue Cao Yu Wang Xuchao Guo Xia Hao College of Information Science and Engineering Shandong Agricultural UniversityTaian271018Shandong ProvinceChina Research Institute of Subtropical Forestry Chinese Academy of ForestryHangzhou 311400Zhejiang ProvinceChina School of Big Data Taishan College of Science and TechnologyTaian271034Shandong ProvinceChina

The new shoot density of slash pine serves as a vital indicator for assessing its growth and photosynthetic capacity,while the number of new shoots offers an intuitive reflection of this *** deep learning methods becoming increasingly popular,automated counting of new shoots has greatly improved in recent years but is still limited by tedious and expensive data collection and *** resolve these issues,this paper proposes a semi-supervised counting network(MTSC-Net)for estimating the number of slash pine new ***,based on the mean-teacher framework,we introduce the improved VGG19 to extract multiscale new shoot ***,to connect local new shoot feature information with global channel features,attention feature fusion module is introduced to achieve effective feature ***,the new shoot density map and density probability distribution are processed in a fine-grained manner through multiscale dilated convolution of the regression head and classification *** addition,a masked image modeling strategy is introduced to encourage the contextual understanding of global new shoot features and improve the counting *** experimental results show that MTSC-Net outperforms other semi-supervised counting models with labeled percentages ranging from 5％to 50％.When the labeled percentage is 5％,the mean absolute error and root mean square error are 17.71 and 25.49,*** findings demonstrate that our work can be used as an efficient semi-supervised counting method to provide automated support for tree breeding and genetic utilization.

关键词： network counting estimating mtsc-net number pine semi-supervised shoots slash

来源：评论

学校读者我要写书评

暂无评论

Resolution-Adaptive Representation Learning via Eliminating Abnormal Features for Cross-Resolution Person Re-Identification 14

Resolution-Adaptive Representation Learning via Eliminating ...

引用

14th International Conference on Information technology in Medicine and Education, ITME 2024

作者： Lu, Xing Lai, Fengshan Cao, Zhixiang Xia, Daoxun Guizhou Normal University School of Big Data and Computer Science Guiyang China Guizhou Normal University Key Laboratory of Information and Computing Science Guizhou Province Guiyang China Guizhou Normal University Engineering Laboratory for Applied Technology of Big Data in Education Guiyang China

ISBN: (纸本)9798350356670

Cross-resolution person re-identification(CR-ReID) seeks to overcome the challenge of retrieving and matching specific person images across cameras with varying resolutions. Numerous existing studies utilize established CNNs and ViTs models to resize captured low-resolution (LR) images and align them with high-resolution (HR) image features. However, these methods overlook the potential feature connections between LR and HR images. Consequently, CNNs or ViTs tend to highlight outliers rather than the intended characteristics in LR image attention maps. In this work, we propose the abnormal feature elimination and reconfiguration transformer (ART) network, a novel network architecture, for robust cross-resolution person re-identification tasks. Our proposed method uses a resolution feature discriminator to learn resolution invariant features and outputs feature matrices of images with different resolutions. We utilize output feature matrices to model LR and HR image interactions through cross-resolution landmark agent attention. We aim to mitigate abnormal image features and prioritize the attention on the target person by learning representations from input images of various resolutions. Extensive evaluations on three real-world datasets confirm the excellent results of our approach. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

data Aggregation Point Placement and Subnetwork Optimization for Smart Grids

引用

Computers, Materials & Continua 2025年第4期83卷 407-434页

作者： Tien-Wen Sung Wei Li Chao-Yang Lee Yuzhen Chen Qingjun Fang Fujian Provincial Key Laboratory of Big Data Mining and Applications College of Computer Science and MathematicsFujian University of TechnologyFuzhou350118China Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin640301TaiwanChina

To transmit customer power data collected by smart meters(SMs)to utility companies,data must first be transmitted to the corresponding data aggregation point(DAP)of the *** number of DAPs installed and the installation location greatly impact the whole *** the traditional DAP placement algorithm,the number of DAPs must be set in advance,but determining the best number of DAPs is difficult,which undoubtedly reduces the overall performance of the ***,the excessive gap between the loads of different DAPs is also an important factor affecting the quality of the *** address the above problems,this paper proposes a DAP placement algorithm,APSSA,based on the improved affinity propagation(AP)algorithm and sparrow search(SSA)algorithm,which can select the appropriate number of DAPs to be installed and the corresponding installation locations according to the number of SMs and their distribution locations in different *** algorithm adds an allocation mechanism to optimize the subnetwork in the *** is evaluated under three different areas and compared with other DAP placement *** experimental results validated that the method in this paper can reduce the network cost,shorten the average transmission distance,and reduce the load gap.

关键词： Smart grid data aggregation point placement network cost average transmission distance load gap

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：